CN107748940B - Power-saving potential quantitative prediction method - Google Patents
Power-saving potential quantitative prediction method Download PDFInfo
- Publication number
- CN107748940B CN107748940B CN201711136988.4A CN201711136988A CN107748940B CN 107748940 B CN107748940 B CN 107748940B CN 201711136988 A CN201711136988 A CN 201711136988A CN 107748940 B CN107748940 B CN 107748940B
- Authority
- CN
- China
- Prior art keywords
- power
- saving potential
- data
- electricity
- prediction
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 29
- 230000005611 electricity Effects 0.000 claims abstract description 21
- 239000003550 marker Substances 0.000 claims abstract description 6
- 238000007621 cluster analysis Methods 0.000 claims abstract description 5
- 238000012549 training Methods 0.000 claims description 24
- 238000012360 testing method Methods 0.000 claims description 13
- 238000004422 calculation algorithm Methods 0.000 claims description 8
- 238000002790 cross-validation Methods 0.000 claims description 7
- 238000003066 decision tree Methods 0.000 claims description 6
- 238000011156 evaluation Methods 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000012795 verification Methods 0.000 claims description 3
- 230000006399 behavior Effects 0.000 abstract description 4
- 230000002354 daily effect Effects 0.000 description 14
- 230000006870 function Effects 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000005265 energy consumption Methods 0.000 description 2
- 238000003064 k means clustering Methods 0.000 description 2
- 238000011158 quantitative evaluation Methods 0.000 description 2
- 238000013139 quantization Methods 0.000 description 2
- 238000010187 selection method Methods 0.000 description 2
- 230000035945 sensitivity Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000010835 comparative analysis Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000004134 energy conservation Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P80/00—Climate change mitigation technologies for sector-wide applications
- Y02P80/10—Efficient use of energy, e.g. using compressed air or pressurized fluid as energy carrier
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Water Supply & Treatment (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to a power-saving potential quantitative prediction method, which comprises the following steps: extracting power utilization data of industrial users, acquiring power utilization characteristic indexes from the power utilization data of the users, and dividing power utilization groups through cluster analysis; and establishing an electricity-saving potential prediction model, selecting a marker post in the same electricity consumption group, and inputting the electricity consumption of the marker post into the electricity-saving potential prediction model to obtain a future electricity-saving potential prediction value. Compared with the prior art, the method has the advantages of quantized power-saving potential, more intuitive guidance of power utilization behaviors, high prediction accuracy and the like.
Description
Technical Field
The invention relates to the field of energy conservation, in particular to a power-saving potential quantitative prediction method.
Background
China enters a high-speed development period of construction and development since twenty-first century, China GDP exceeds Japan to become the second largest economic body in the world in 2010, and China possibly favors the United states to become the first largest energy consumption country in the world in the future, but the unit GDP energy consumption of China is still about three times of the world average level and is in a quite laggard position internationally.
Therefore, the power saving potential of the user is evaluated, and the power saving potential is quantitatively calculated, so that power saving reminding and early warning are provided for the user with high power consumption, and contribution to social energy saving is facilitated.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provide a power saving potential quantitative prediction method.
The purpose of the invention can be realized by the following technical scheme:
a method for power saving potential quantization prediction, the method comprising the steps of:
s1, extracting power utilization data of industrial users, acquiring power utilization characteristic indexes from the power utilization data of the users, and dividing power utilization groups through cluster analysis;
and S2, establishing an electricity-saving potential prediction model, selecting a marker post in the same electricity consumption group, and inputting the electricity consumption of the marker post into the electricity-saving potential prediction model to obtain a future electricity-saving potential prediction value.
Preferably, when the electricity consumption data of the industrial users are extracted in step S1, the power data are collected at intervals of 15min, and the power data are collected at 96 points per day.
Preferably, the electricity characteristic index at step S1 includes a daily average electricity usage, a daily average peak electricity usage, a daily average valley electricity usage, a peak-valley electricity ratio, and a daily average load factor.
Preferably, the step of dividing the electricity consumption group through the cluster analysis in the step S1 specifically includes the steps of:
s101, adopting a classification accuracy index to self-adaptively select an optimal clustering number;
s102, selecting k centers mukAn initial value of (d);
s103, classifying each data point into a cluster represented by a central point closest to the data point;
s104, acquiring a new central point mu of each clusterkAnd repeating S103 until the maximum step number or the difference between the function values of the clustering criteria before and after is smaller than the set threshold value.
Preferably, the step S2 of establishing the power saving potential prediction model specifically includes the following steps:
s201: taking weather and social factor historical data as input, and taking daily power saving potential of a target user as output to form a sample data set D;
s202, a training set and a testing set are respectively formed by using a cross verification method, and an electricity-saving potential prediction model is established by using an XGboost decision tree algorithm.
Preferably, the establishing of the power saving potential prediction model by using the XGBoost decision tree algorithm specifically comprises: setting XGboost model parameters including basic parameters and training parameters, training the model, judging the prediction accuracy of the model by using the parameters of the test set after the training is finished, resetting the parameters if the prediction accuracy does not meet the set value, and continuing the training until the accuracy requirement is met.
Preferably, the step S202 of using the cross-validation method to respectively form the training set and the test set specifically includes: and (3) dividing the data set D into D1-D10 in equal proportion, taking D1 as a test set, taking D2-D10 as a training set, calculating an evaluation index, taking D2 as the test set, taking D1 and D3-D10 as the training set, and performing prediction model evaluation index calculation by adopting a cross validation method in each iteration process.
Compared with the prior art, the invention has the following advantages:
1. through the prediction of the power saving potential, the user can be reminded in advance when the power saving potential is higher in the future, the power utilization habit of the user is concerned, and the user with high power consumption is urged to carry out power saving reconstruction in time;
2. the power saving potential is quantized, and the power utilization behavior is guided more intuitively.
3. The training model refers to meteorological and social factor historical data, the model is evaluated by adopting a cross validation method, the prediction result is accurate, and better prediction accuracy can be realized only by using the prediction data of several factors with the highest sensitivity.
Drawings
Fig. 1 is a flow chart of a power saving potential quantization prediction method according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, not all, embodiments of the present invention. All other embodiments, which can be obtained by a person skilled in the art without any inventive step based on the embodiments of the present invention, shall fall within the scope of protection of the present invention.
Examples
The invention discloses a power-saving potential quantitative prediction method, which applies big data correlation technology and provides a complete user power-saving analysis method, and mainly comprises three modules: firstly, carrying out group division on industries, calculating power utilization characteristic indexes of all users in a certain industry, and dividing the power utilization characteristic indexes into typical power utilization groups with similar scales and comparability through clustering analysis; secondly, performing further comparative analysis in the same group, calculating scores of all indexes of the users in the group, quantitatively evaluating the power saving potential of each user by taking the average level of the group as a reference, predicting the power saving potential, modeling each user through historical data, and predicting the power saving potential of five days in the future; and finally, analyzing the influence factors of the power saving potential of the user and the power saving strategy from the typical power consumption behavior, the power price and the environment perception of the user so as to guide the power consumption behavior of the user. The specific flow is shown in figure 1:
industry group division
1. Electrical characteristic index extraction
Except for the traditional collected data such as peak-valley electric quantity and daily frozen electric quantity, large industrial and commercial users and partial residential users in east China with the power consumption of more than 100kW begin to collect 15min as interval power data, the number of the interval power data is 96 points every day, and the electricity consumption characteristic description indexes are as follows:
Xk＝{α1,...,αu；β1,...,βν；f1,...,fl}；
k＝1,2,...m
wherein alpha represents daily 96-point power time sequence data, beta represents monthly electricity consumption time sequence data, f represents non-time sequence evaluation parameters, including daily average electricity consumption, daily average peak electricity consumption, daily average valley electricity consumption, peak-valley electricity ratio, daily average load rate, and m represents the number of samples.
2. Division of industry power utilization group
On the basis of extracting the user electricity utilization characteristic indexes, clustering users in the same industry by adopting a statistical distance-based K-means clustering algorithm. Because the quality levels of the time sequence data acquired on site are not uniform, and some points are lost and abnormal sometimes, a K-means clustering algorithm based on statistical distance is adopted, the algorithm receives a parameter K, and then n data objects input in advance are divided into K clusters so as to ensure that the obtained clusters meet the conditions that the object similarity in the same cluster is higher and the object similarity in different clusters is smaller, and the method comprises the following specific steps:
1) adopting a classification accuracy Index (DBI) to self-adaptively select an optimal clustering number, and adopting a calculation formula of
In the formula Ci，CjRepresents the mean distance within class, wi，wjRepresenting the cluster center distance.
2) Selecting K center mukThe initial value of (c). This process is usually a heuristic selection method for a specific problem, or in most cases a random selection method. Since it was previously said that K-means cannot guarantee completenessThe selection of the real and initial values of the local optimal solution and whether the global optimal solution can be converged to have a great relationship.
3) Each data point is classified into cluster represented by the center point closest to it, wherein the distance calculation formula does not adopt Euclidean distance, but selects statistical distance, which is defined as dij＝(eij 2+sij 2)0.5Wherein d isijRepresents the distance between curve i and curve j (the distance between data point i and the class j center point), eijRepresenting the horizontal distance, s, between the data points i and the class j center pointsijRepresenting the distance in the vertical direction between the data point i and the class j center point.
4) Calculating new central point of each cluster by formula
5) Repeating step 3) until the maximum number of steps is iterated or the difference between the values of J before and after the iteration is less than a threshold value.
Wherein tau isnk1 when data point n is classified into cluster k, and 0, τ otherwisenkFor a data point N belonging to a class coefficient of a cluster k, N representing the number of data points, xnRepresenting the sample value, mukRepresenting the center point value.
Power saving potential quantitative evaluation and prediction
1. Power saving potential quantitative evaluation
After an industrial power utilization group is obtained, an electricity-saving benchmark in the power utilization group is selected, the group mean value is used as the electricity-saving benchmark of the group according to the index of daily average power consumption, and after the electricity-saving benchmark is obtained, the electricity-saving potential of a target user can be obtained by subtracting the daily power consumption of the target user and the electricity-saving benchmark.
2. Short term power saving potential prediction
The method comprises the steps of taking weather and social factor historical data as input, taking daily electricity-saving potential of a target user as output, forming a sample data set D, respectively forming a training set and a testing set by using a cross verification method, and establishing an electricity-saving potential prediction model by using an XGboost algorithm. The model adopts 10-fold cross validation, the data set D is divided into D1-D10 in an equal proportion, D1 is used as a test set, D2-D10 is used as a training set, evaluation indexes are calculated, then D2 is used as the test set, D1 and D3 … D10 are used as the training set, and the like. And in each iteration process, evaluating the model by adopting a cross validation method. After the model is established, the future short-term electricity-saving potential value can be predicted by using the high-precision numerical weather forecast prediction result of the prediction day and social information such as whether the prediction day is a working day.
A tree is trained using a training set (sample true values) to build a decision tree model, and the complexity of the model is limited by adding regularization terms to prevent overfitting. The result can then be predicted on the real observations by means of this decision tree.
The method for establishing the prediction model comprises the following steps: setting model parameters of the XGboost, including basic parameters and training parameters, such as a base classifier, the number of threads, the maximum depth of a tree, the learning rate, the iteration times and the like; starting to train the model; evaluating the model after training the model; if the prediction accuracy of the model meets the requirement, storing the trained model, otherwise resetting the parameters and carrying out the training again until the prediction accuracy of the model meets the requirement; the trained model is saved as a file with a certain format, such as xgboost model, and the model can predict the node potential value from the input data.
The XGboost model prediction function is as follows:
wherein h isiIs the weight of the node, giIs a gradient, λ is a constant term;
the objective function is:
in the Obj, the number of the columns is,
for the second-order expression after Taylor expansion of the penalty function defining the complexity of the tree model, GjIs a gradient of the hierarchy, HjThe weight of a node is defined as λ, a constant term, and γ T is defined as the number of nodes.
Influence factor of power saving
The method has the advantages that the prediction accuracy of the high-sensitivity factors of the power saving potential is preferentially ensured, the key for improving the prediction accuracy of the power saving potential is realized, and under the condition that prediction data source information such as weather is incomplete, better prediction accuracy can be realized only by providing prediction data of several factors with the highest sensitivity. Through the prediction of the power saving potential, the user can be reminded in advance when the power saving potential is higher in the future, the power utilization habit of the user is concerned, and the user with high power consumption is urged to perform power saving reconstruction in time.
While the invention has been described with reference to specific embodiments, the invention is not limited thereto, and various equivalent modifications and substitutions can be easily made by those skilled in the art within the technical scope of the invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (2)
1. A power saving potential quantitative prediction method is characterized by comprising the following steps:
s1, extracting power utilization data of industrial users, acquiring power utilization characteristic indexes from the power utilization data of the users, and dividing power utilization groups through cluster analysis;
s2, establishing an electricity-saving potential prediction model, selecting a marker post in the same electricity consumption group, and inputting the electricity consumption of the marker post into the electricity-saving potential prediction model to obtain a future electricity-saving potential prediction value;
the power consumption characteristic indexes of the step S1 comprise daily average power consumption, daily average peak power consumption, daily average valley power consumption, peak-valley power ratio and daily average load factor;
the step of dividing the electricity consumption group through the cluster analysis described in the step S1 specifically includes the steps of:
s101, adopting a classification accuracy index to self-adaptively select an optimal clustering number;
s102, selecting k centers mukAn initial value of (d);
s103, classifying each data point into a cluster represented by a central point closest to the data point;
s104, acquiring a new central point mu of each clusterkRepeating S103 until the maximum step number or the difference between the function values of the clustering criteria before and after is smaller than a set threshold value;
the step S2 of establishing the power saving potential prediction model specifically includes the following steps:
s201: taking weather and social factor historical data as input, and taking daily power saving potential of a target user as output to form a sample data set D;
s202, respectively forming a training set and a testing set by using a cross verification method, and establishing a power saving potential prediction model by using an XGboost decision tree algorithm;
the specific steps of establishing the power saving potential prediction model by utilizing the XGboost decision tree algorithm are as follows: setting XGboost model parameters including basic parameters and training parameters, training the model, judging the prediction accuracy of the model by using test set parameters after the training is finished, resetting the parameters if the prediction accuracy does not meet a set value, and continuing the training until the accuracy requirement is met;
in step S202, the forming of the training set and the testing set by using the cross-validation method specifically includes: and (3) dividing the data set D into D1-D10 in equal proportion, taking D1 as a test set, taking D2-D10 as a training set, calculating an evaluation index, taking D2 as the test set, taking D1 and D3-D10 as the training set, and performing prediction model evaluation index calculation by adopting a cross validation method in each iteration process.
2. The quantitative prediction method for power saving potential according to claim 1, wherein in the step S1, when the power consumption data of the industrial users are extracted, power data are collected at intervals of 15min, and the power data are collected at 96 points per day.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711136988.4A CN107748940B (en) | 2017-11-16 | 2017-11-16 | Power-saving potential quantitative prediction method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711136988.4A CN107748940B (en) | 2017-11-16 | 2017-11-16 | Power-saving potential quantitative prediction method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107748940A CN107748940A (en) | 2018-03-02 |
| CN107748940B true CN107748940B (en) | 2021-10-12 |
Family
ID=61251158
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711136988.4A Active CN107748940B (en) | 2017-11-16 | 2017-11-16 | Power-saving potential quantitative prediction method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107748940B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109753990B (en) * | 2018-11-27 | 2022-08-19 | 国网江苏省电力有限公司电力科学研究院 | User electric energy substitution potential prediction method, system and storage medium |
| CN110298552B (en) * | 2019-05-31 | 2023-12-01 | 国网上海市电力公司 | Power distribution network individual power abnormality detection method combining historical electricity utilization characteristics |
| CN111523819B (en) * | 2020-04-28 | 2023-04-21 | 重庆涪陵电力实业股份有限公司 | Energy-saving potential evaluation method considering uncertainty of output power of distributed power supply |
| CN111612055B (en) * | 2020-05-15 | 2020-12-04 | 北京中科三清环境技术有限公司 | Weather situation typing method, air pollution condition prediction method and device |
| CN112785118B (en) * | 2020-12-24 | 2024-01-26 | 南京华盾电力信息安全测评有限公司 | Month electricity consumption prediction analysis method for small-sized electricity selling company agent user |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2397926A2 (en) * | 2010-06-18 | 2011-12-21 | General Electric Company | A self-healing power grid and method thereof |
| CN103268115A (en) * | 2013-06-14 | 2013-08-28 | 鲁电集团有限公司 | Power demand side monitoring system and method |
| CN103729695A (en) * | 2014-01-06 | 2014-04-16 | 国家电网公司 | Short-term power load forecasting method based on particle swarm and BP neural network |
| CN104008430A (en) * | 2014-05-29 | 2014-08-27 | 华北电力大学 | Method for establishing virtual reality excavation dynamic smart load prediction models |
| CN104318316A (en) * | 2014-10-09 | 2015-01-28 | 中国科学院自动化研究所 | Method of measuring user electricity utilization in real time |
| CN104361452A (en) * | 2014-11-14 | 2015-02-18 | 云南电网公司 | Big consumer abnormal electricity consumption pre-warning system with multiple networks integrated |
| CN105117979A (en) * | 2015-08-19 | 2015-12-02 | 中国电力科学研究院 | Commercial building demand response potential assessment method |
| CN105184455A (en) * | 2015-08-20 | 2015-12-23 | 国家电网公司 | High dimension visualized analysis method facing urban electric power data analysis |
| CN105719058A (en) * | 2016-01-15 | 2016-06-29 | 国网江西省电力科学研究院 | Electric power demand-side management auxiliary decision support system |
| CN106022646A (en) * | 2016-06-08 | 2016-10-12 | 国网上海市电力公司 | Electric power user information data analysis system and analysis method |
| CN106503439A (en) * | 2016-10-21 | 2017-03-15 | 国网福建省电力有限公司 | A kind of method of the collection fault early warning system based on data mining |
| CN106651200A (en) * | 2016-12-29 | 2017-05-10 | 中国西电电气股份有限公司 | Electrical load management method and system for industrial enterprise aggregate user |
-
2017
- 2017-11-16 CN CN201711136988.4A patent/CN107748940B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2397926A2 (en) * | 2010-06-18 | 2011-12-21 | General Electric Company | A self-healing power grid and method thereof |
| CN103268115A (en) * | 2013-06-14 | 2013-08-28 | 鲁电集团有限公司 | Power demand side monitoring system and method |
| CN103729695A (en) * | 2014-01-06 | 2014-04-16 | 国家电网公司 | Short-term power load forecasting method based on particle swarm and BP neural network |
| CN104008430A (en) * | 2014-05-29 | 2014-08-27 | 华北电力大学 | Method for establishing virtual reality excavation dynamic smart load prediction models |
| CN104318316A (en) * | 2014-10-09 | 2015-01-28 | 中国科学院自动化研究所 | Method of measuring user electricity utilization in real time |
| CN104361452A (en) * | 2014-11-14 | 2015-02-18 | 云南电网公司 | Big consumer abnormal electricity consumption pre-warning system with multiple networks integrated |
| CN105117979A (en) * | 2015-08-19 | 2015-12-02 | 中国电力科学研究院 | Commercial building demand response potential assessment method |
| CN105184455A (en) * | 2015-08-20 | 2015-12-23 | 国家电网公司 | High dimension visualized analysis method facing urban electric power data analysis |
| CN105719058A (en) * | 2016-01-15 | 2016-06-29 | 国网江西省电力科学研究院 | Electric power demand-side management auxiliary decision support system |
| CN106022646A (en) * | 2016-06-08 | 2016-10-12 | 国网上海市电力公司 | Electric power user information data analysis system and analysis method |
| CN106503439A (en) * | 2016-10-21 | 2017-03-15 | 国网福建省电力有限公司 | A kind of method of the collection fault early warning system based on data mining |
| CN106651200A (en) * | 2016-12-29 | 2017-05-10 | 中国西电电气股份有限公司 | Electrical load management method and system for industrial enterprise aggregate user |
Non-Patent Citations (2)
| Title |
|---|
| XGBoost在超短期负荷预测中的应用;杨修德，等;《电气传动自动化》;20170801;第39卷(第4期);期刊第21-25页 * |
| 能效电厂项目的节电潜力分析;王晶晶;《中国优秀硕士学位论文全文数据库工程科技II辑》;20150115(第1期);论文第8-14页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107748940A (en) | 2018-03-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107748940B (en) | Power-saving potential quantitative prediction method | |
| CN112949945B (en) | Wind power ultra-short-term prediction method for improving bidirectional long-term and short-term memory network | |
| WO2022135265A1 (en) | Failure warning and analysis method for reservoir dispatching rules under effects of climate change | |
| JP6129028B2 (en) | Energy consumption prediction method for building power equipment | |
| CN106022528B (en) | A kind of photovoltaic plant short term power prediction technique based on density peaks hierarchical clustering | |
| CN111178611B (en) | Method for predicting daily electric quantity | |
| CN107194495B (en) | Photovoltaic power longitudinal prediction method based on historical data mining | |
| CN106485262A (en) | A kind of bus load Forecasting Methodology | |
| CN112100911B (en) | Solar radiation prediction method based on depth BILSTM | |
| CN113554466A (en) | Short-term power consumption prediction model construction method, prediction method and device | |
| CN106529731A (en) | Regional power grid photovoltaic power station cluster division method | |
| CN105809349B (en) | Dispatching method for step hydropower station group considering incoming water correlation | |
| Zhuang et al. | Long-lead prediction of extreme precipitation cluster via a spatiotemporal convolutional neural network | |
| CN115907822A (en) | Load characteristic index relevance mining method considering region and economic influence | |
| CN113344288A (en) | Method and device for predicting water level of cascade hydropower station group and computer readable storage medium | |
| CN116739172A (en) | Method and device for ultra-short-term prediction of offshore wind power based on climbing identification | |
| CN115545333A (en) | Method for predicting load curve of multi-load daily-type power distribution network | |
| CN105488598A (en) | Medium-and-long time electric power load prediction method based on fuzzy clustering | |
| CN117933316B (en) | Groundwater level probability forecasting method based on interpretable Bayesian convolution network | |
| CN112200209A (en) | Poor user identification method based on day-to-day power consumption | |
| CN113919729A (en) | Regional three-generation space influence and cooperation level evaluation method and system | |
| CN102508997B (en) | Underground water model output uncertainty analysis method | |
| Zhou et al. | Pre-clustering active learning method for automatic classification of building structures in urban areas | |
| CN113762591A (en) | Short-term electric quantity prediction method and system based on GRU and multi-core SVM counterstudy | |
| CN117077005B (en) | Optimization method and system for urban micro-update potential |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB02 | Change of applicant information |
Address after: 200002 No. 181 East Nanjing Road, Shanghai, Huangpu District Applicant after: STATE GRID SHANGHAI MUNICIPAL ELECTRIC POWER Co. Applicant after: EAST CHINA ELECTRIC POWER RESEARCH INSTITUTE Co.,Ltd. Applicant after: Star link information technology (Shanghai) Co.,Ltd. Address before: 200002 No. 181 East Nanjing Road, Shanghai, Huangpu District Applicant before: STATE GRID SHANGHAI MUNICIPAL ELECTRIC POWER Co. Applicant before: EAST CHINA ELECTRIC POWER RESEARCH INSTITUTE Co.,Ltd. Applicant before: TRANSWARP TECHNOLOGY (SHANGHAI) Co.,Ltd. |
|
| CB02 | Change of applicant information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |